High Sparsity Research Articles

Network Embedding via Deep Prediction Model

Network-structured data becomes ubiquitous in daily life and is growing at a rapid pace. It presents great challenges to feature engineering due to the high non-linearity and sparsity of the data. The local and global structure of the real-world networks can be reflected by dynamical transfer behaviors among nodes. This paper proposes a network embedding framework to capture the transfer behaviors on structured networks via deep prediction models. We first design a degree-weight biased random walk model to capture the transfer behaviors on the network. Then a deep network embedding method is introduced to preserve the transfer possibilities among the nodes. A network structure embedding layer is added into conventional deep prediction models, including Long Short-Term Memory Network and Recurrent Neural Network, to utilize the sequence prediction ability. To keep the local network neighborhood, we further perform a Laplacian supervised space optimization on the embedding feature representations. Experimental studies are conducted on various datasets including social networks, citation networks, biomedical network, collaboration network and language network. The results show that the learned representations can be effectively used as features in a variety of tasks, such as clustering, visualization, classification, reconstruction and link recovery, and achieve promising performance compared with state-of-the-arts.

Efficient Spectral Graph Convolutional Network Deployment on Memristive Crossbars

Graph Neural Networks (GNNs) have attracted increasing research interest for their remarkable capability to model graph-structured knowledge. However, GNNs suffer from intensive data exchange and poor data locality, which will cause critical performance and energy bottlenecks under conventional complementary metal oxide semiconductor (CMOS)-based von-Neumann computing architectures (graphics processing unit (GPU), central processing unit (CPU)) for the “Memory Wall” issue. Fortunately, memristive crossbar-based computation has emerged as one of the most promising neuromorphic computing architectures, which has been widely studied as the computing platform for convolutional neural network (CNNs), recurrent neural network (RNNs), spiking neural network (SNNs), etc. This paper proposes the deployment of spectral graph convolutional networks (GCNs) on memristive crossbars. Further, based on the structure of GCNs (extremely high sparsity and unbalanced non-zero data distribution) and the neuromorphic characteristics of memristive crossbar circuit, we propose the acceleration method that consists of Sparse Laplace Matrix Reordering and Diagonal Block Matrix Multiplication. The simulated experiment on memristor crossbars achieves 90.3% overall accuracy on the supervised learning graph dataset (QM7), and compared with the original computation, the proposed acceleration computing framework (with half-size diagonal blocks) achieves a 27.3% reduction of memristor number. Additionally, on the unsupervised learning dataset (Karate club), our method shows no loss of accuracy with half-size diagonal block mapping and reaches a 32.2% reduction of memristor number.

Identify Best Learning Method for Heart Diseases Prediction Under impact of Different Datasets Characteristics

This paper introduces an experimental study of the heart disease datasets characteristics impact on the performance of classification algorithms in the aim of identifying the best algorithm for each dataset under its characteristics. The performance of five machine learning algorithms (logistic regression (LR), K-Nearest Neighbor (KNN), Decision tree (DT), Random Forest (RF), and support vector machine (SVM)), single layer neural network (ANN), and deep neural network (DNN), has been evaluated using five heart disease datasets under four data complexity measurement: number of samples (dataset size), number of features (dimension of dataset), Data sparsity measures, and correlation of features. All datasets have been processed and normalized then the mutual information-based feature selection method was used to solve the overfitting problem. The results show that in general, the machine learning especially the Random Forest algorithm achieves high classification accuracy than deep learning network. In other hand, the high sparsity and less mutual information of dataset has large impact on degradation of the performance of classification algorithms than other characteristics of data.

Con-AAE: Contrastive Cycle Adversarial Autoencoders for Single-cell Multi-omics Alignment and Integration.

We have entered the multi-omics era and can measure cells from different aspects. Hence, we can get a more comprehensive view by integrating or matching data from different spaces corresponding to the same object. However, it is particularly challenging in the single-cell multi-omics scenario because such data are very sparse with extremely high dimensions. Though some techniques can be used to measure scATAC-seq and scRNA-seq simultaneously, the data are usually highly noisy due to the limitations of the experimental environment. To promote single-cell multi-omics research, we overcome the above challenges, proposing a novel framework, contrastive cycle adversarial autoencoders, which can align and integrate single-cell RNA-seq data and single-cell ATAC-seq data. Con-AAE can efficiently map the above data with high sparsity and noise from different spaces to a coordinated subspace, where alignment and integration tasks can be easier. We demonstrate its advantages on several datasets. Zenodo link: https://zenodo.org/badge/latestdoi/368779433 github: https://github.com/kakarotcq/Con-AAE. Supplementary data are available at Bioinformatics online.

Vibration-based incipient surge detection and diagnosis of the centrifugal compressor using adaptive feature fusion and sparse ensemble learning approach

As a critical high-speed rotating machinery, the centrifugal compressor has been widely used in various modern industries. However, it is subject to a potential damaging phenomenon called surge that can be caused by several factors such as unmatched design, improper operation, inlet and outlet blockage, and so on, which thus may result in catastrophic accidents. This paper concerns the incipient surge detection and diagnosis (ISDD) of the centrifugal compressor based on its bearing vibration signals, leveraging adaptive feature fusion and sparse ensemble learning approach to develop a data-driven-based intelligent diagnostic model. Firstly, vibration signals are decomposed by the empirical mode decomposition (EMD) method, and various features can be extracted from the obtained intrinsic mode functions (IMFs) with rich information of the time series. Next, maximum likelihood estimation (MLE) is utilized to compute the intrinsic dimension of the extracted feature vectors, which are then reduced to the corresponding dimensionality adaptively by kernel principal component analysis (kernel PCA). Coping with the multi-dimensional input and nonlinearly separable classification problem, an ensemble learning approach with L1-regularization term is adopted for incipient surge identification of the centrifugal compressor. A novel and hyperparameter-relaxed hybrid algorithm is employed for the sparse ensemble learning procedure, which guarantees transcendental accuracy and preeminent generalization capability while ensuring high robustness and sparsity of the intelligent model. Finally, in addition to diagnostic tasks of the centrifugal compressor datasets under different working conditions, the ISDD performance of the proposed method in imbalanced sample scenarios, varying working conditions and additional noise interference circumstances is comprehensively investigated, and the overall success indicates the robustness and superiority of the proposed method compared with other existing approaches.

ScMCs: a framework for single-cell multi-omics data integration and multiple clusterings.

The integration of single-cell multi-omics data can uncover the underlying regulatory basis of diverse cell types and states. However, contemporary methods disregard the omics individuality, and the high noise, sparsity, and heterogeneity of single-cell data also impact the fusion effect. Furthermore, available single-cell clustering methods only focus on the cell type clustering, which cannot mine the alternative clustering to comprehensively analyze cells. We propose a single-cell data fusion based multiple clustering (scMCs) approach that can jointly model single-cell transcriptomics and epigenetic data, and explore multiple different clusterings. scMCs first mines the omics-specific and cross-omics consistent representations, then fuses them into a co-embedding representation, which can dissect cellular heterogeneity and impute data. To discover the potential alternative clustering embedded in multi-omics, scMCs projects the co-embedding representation into different salient subspaces. Meanwhile, it reduces the redundancy between subspaces to enhance the diversity of alternative clusterings and optimizes the cluster centers in each subspace to boost the quality of corresponding clustering. Unlike single clustering, these alternative clusterings provide additional perspectives for understanding complex genetic information, such as cell types and states. Experimental results show that scMCs can effectively identify subcellular types, impute dropout events, and uncover diverse cell characteristics by giving different but meaningful clusterings. The code is available at www.sdu-idea.cn/codes.php?name=scMCs.

A soft computing approach for software defect density prediction

AbstractDefect density is an essential software testing and maintenance aspect that determines the quality of software products. It is used as a management factor to distribute limited human resources successfully. The availability of public defect datasets facilitates building defect density prediction models using established static code metrics. Since the data gathered for software modules are often subject to uncertainty, it becomes difficult to deliver accurate and reliable predictions. To alleviate this issue, we propose a new prediction model that integrates gray system theory and fuzzy logic to handle the imprecision in software measurement. We propose a new similarity measure that combines the benefits of fuzzy logic and gray relational analysis. The proposed model was validated against defect density prediction models using public defect datasets. The defect density variable is frequently sparse because of the vast number of none‐defected modules in the datasets. Therefore, we also check our proposed model's performance against the sparsity level. The findings reveal that the developed model surpasses other defect density prediction models over the datasets with high and very high sparsity ratios. The ensemble learning techniques are competitive choices to the proposed model when the sparsity ratio is relatively small. On the other hand, the statistical regression models were the most inadequate methods for such problems and datasets. Finally, the proposed model was evaluated against different degrees of uncertainty using a sensitivity analysis procedure. The results showed that our model behaves stably under different degrees of uncertainty.

UnsupervisedEHR‐based phenotyping via matrix and tensor decompositions

AbstractComputational phenotyping allows for unsupervised discovery of subgroups of patients as well as corresponding co‐occurring medical conditions from electronic health records (EHR). Typically, EHR data contains demographic information, diagnoses and laboratory results. Discovering (novel) phenotypes has the potential to be of prognostic and therapeutic value. Providing medical practitioners with transparent and interpretable results is an important requirement and an essential part for advancing precision medicine. Low‐rank data approximation methods such as matrix (e.g., nonnegative matrix factorization) and tensor decompositions (e.g., CANDECOMP/PARAFAC) have demonstrated that they can provide such transparent and interpretable insights. Recent developments have adapted low‐rank data approximation methods by incorporating different constraints and regularizations that facilitate interpretability further. In addition, they offer solutions for common challenges within EHR data such as high dimensionality, data sparsity and incompleteness. Especially extractingtemporal phenotypesfrom longitudinal EHR has received much attention in recent years. In this paper, we provide a comprehensive review of low‐rank approximation‐based approaches for computational phenotyping. The existing literature is categorized into temporal versus static phenotyping approaches based on matrix versus tensor decompositions. Furthermore, we outline different approaches for the validation of phenotypes, that is, the assessment of clinical significance.This article is categorized under:Algorithmic Development > Structure DiscoveryFundamental Concepts of Data and Knowledge > Explainable AITechnologies > Machine Learning

Trainable quantization for Speedy Spiking Neural Networks.

Spiking neural networks are considered as the third generation of Artificial Neural Networks. SNNs perform computation using neurons and synapses that communicate using binary and asynchronous signals known as spikes. They have attracted significant research interest over the last years since their computing paradigm allows theoretically sparse and low-power operations. This hypothetical gain, used from the beginning of the neuromorphic research, was however limited by three main factors: the absence of an efficient learning rule competing with the one of classical deep learning, the lack of mature learning framework, and an important data processing latency finally generating energy overhead. While the first two limitations have recently been addressed in the literature, the major problem of latency is not solved yet. Indeed, information is not exchanged instantaneously between spiking neurons but gradually builds up over time as spikes are generated and propagated through the network. This paper focuses on quantization error, one of the main consequence of the SNN discrete representation of information. We argue that the quantization error is the main source of accuracy drop between ANN and SNN. In this article we propose an in-depth characterization of SNN quantization noise. We then propose a end-to-end direct learning approach based on a new trainable spiking neural model. This model allows adapting the threshold of neurons during training and implements efficient quantization strategies. This novel approach better explains the global behavior of SNNs and minimizes the quantization noise during training. The resulting SNN can be trained over a limited amount of timesteps, reducing latency, while beating state of the art accuracy and preserving high sparsity on the main datasets considered in the neuromorphic community.

ScGCL: an imputation method for scRNA-seq data based on graph contrastive learning.

Single-cell RNA-sequencing (scRNA-seq) is widely used to reveal cellular heterogeneity, complex disease mechanisms and cell differentiation processes. Due to high sparsity and complex gene expression patterns, scRNA-seq data present a large number of dropout events, affecting downstream tasks such as cell clustering and pseudo-time analysis. Restoring the expression levels of genes is essential for reducing technical noise and facilitating downstream analysis. However, existing scRNA-seq data imputation methods ignore the topological structure information of scRNA-seq data and cannot comprehensively utilize the relationships between cells. Here, we propose a single-cell Graph Contrastive Learning method for scRNA-seq data imputation, named scGCL, which integrates graph contrastive learning and Zero-inflated Negative Binomial (ZINB) distribution to estimate dropout values. scGCL summarizes global and local semantic information through contrastive learning and selects positive samples to enhance the representation of target nodes. To capture the global probability distribution, scGCL introduces an autoencoder based on the ZINB distribution, which reconstructs the scRNA-seq data based on the prior distribution. Through extensive experiments, we verify that scGCL outperforms existing state-of-the-art imputation methods in clustering performance and gene imputation on 14 scRNA-seq datasets. Further, we find that scGCL can enhance the expression patterns of specific genes in Alzheimer's disease datasets. The code and data of scGCL are available on Github: https://github.com/zehaoxiong123/scGCL. Supplementary data are available at Bioinformatics online.

Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction

This work is focused on the UnSparse-Opt framework for the efficient unstructured pruning and quantisation of feedforward neural networks and the improvement of their efficiency on graphic processing units (GPU) by using a direct sparse algorithm. The Nvidia deep neural network (cuDnn) library is the most effective implementation of deep learning (DL) algorithms for GPUs. One of the most common techniques for improving the efficiency of Convolutional Neural Network (CNN) models is weight pruning and quantisation. There are two main types of pruning: structural and non-structural. The first enables much easier acceleration on many type of accelerators, but with structural it is difficult to achieve a sparsity level and accuracy as high as that obtained with the non-structural version. Non-structural pruning with retraining can generate the weight tensors up to ∼90% or more of sparsity in some deep CNN models. In this article, the pruning algorithm is presented which achieve high sparsity levels without drop in accuracy. In the next stage, the linear and non-linear quantisation is adapted for further reductions in time and memory footprint. Additionally, this work presents real CNN models pruned with high sparsities in which some subset of layers can have comparable or better efficiency than cuDnn by using a direct sparse method. Finally, it shows sparse CNN-based architectures with reduced precision which can be more efficient than CuDnn library.

A Hybrid Machine Learning Approach to Screen Optimal Predictors for the Classification of Primary Breast Tumors from Gene Expression Microarray Data.

The high dimensionality and sparsity of the microarray gene expression data make it challenging to analyze and screen the optimal subset of genes as predictors of breast cancer (BC). The authors in the present study propose a novel hybrid Feature Selection (FS) sequential framework involving minimum Redundancy-Maximum Relevance (mRMR), a two-tailed unpaired t-test, and meta-heuristics to screen the most optimal set of gene biomarkers as predictors for BC. The proposed framework identified a set of three most optimal gene biomarkers, namely, MAPK 1, APOBEC3B, and ENAH. In addition, the state-of-the-art supervised Machine Learning (ML) algorithms, namely Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Neural Net (NN), Naïve Bayes (NB), Decision Tree (DT), eXtreme Gradient Boosting (XGBoost), and Logistic Regression (LR) were used to test the predictive capability of the selected gene biomarkers and select the most effective breast cancer diagnostic model with higher values of performance matrices. Our study found that the XGBoost-based model was the superior performer with an accuracy of 0.976 ± 0.027, an F1-Score of 0.974 ± 0.030, and an AUC value of 0.961 ± 0.035 when tested on an independent test dataset. The screened gene biomarkers-based classification system efficiently detects primary breast tumors from normal breast samples.

Decentralized Collaborative Learning Framework for Next POI Recommendation

Next Point-of-Interest (POI) recommendation has become an indispensable functionality in Location-based Social Networks (LBSNs) due to its effectiveness in helping people decide the next POI to visit. However, accurate recommendation requires a vast amount of historical check-in data, thus threatening user privacy as the location-sensitive data needs to be handled by cloud servers. Although there have been several on-device frameworks for privacy-preserving POI recommendations, they are still resource intensive when it comes to storage and computation, and show limited robustness to the high sparsity of user-POI interactions. On this basis, we propose a novel d ecentralized c ollaborative l earning framework for POI r ecommendation (DCLR), which allows users to train their personalized models locally in a collaborative manner. DCLR significantly reduces the local models’ dependence on the cloud for training, and can be used to expand arbitrary centralized recommendation models. To counteract the sparsity of on-device user data when learning each local model, we design two self-supervision signals to pretrain the POI representations on the server with geographical and categorical correlations of POIs. To facilitate collaborative learning, we innovatively propose to incorporate knowledge from either geographically or semantically similar users into each local model with attentive aggregation and mutual information maximization. The collaborative learning process makes use of communications between devices while requiring only minor engagement from the central server for identifying user groups, and is compatible with common privacy preservation mechanisms like differential privacy. We evaluate DCLR with two real-world datasets, where the results show that DCLR outperforms state-of-the-art on-device frameworks and yields competitive results compared with centralized counterparts.

A Comprehensive Performance Model of Sparse Matrix-Vector Multiplication to Guide Kernel Optimization

Sparse Matrix-Vector Multiplication (SpMV) is important in scientific and industrial applications and remains a well-known challenge for modern CPUs due to high sparsity and irregularity. Many researchers try to improve SpMV performance by designing dedicated data formats and computation patterns. However, out-of-order superscalar CPUs have complex micro-architectures where exist complicated interactions and restrictions among software and hardware factors. It is hard to systematically study the effectiveness of optimization methods on the overall performance, as its benefits may be undermined by other factors. In this paper, we thoroughly study the execution of SpMV on modern CPUs and propose a comprehensive performance model to reveal the critical factors and their relationships. Specifically, we first study the coding characteristics of SpMV kernels to identify key factors worthy of attention. Then we model the execution of SpMV as two overlapped parts: CPU pipeline and memory latency. Both are carefully modeled with related hardware and software factors. We also model SIMD performance with the usage of specific SIMD instructions and vector registers. Experiments show that our model matches the actual execution of real-world processors. Guided by the model, we propose SpV8, a novel SpMV kernel that optimizes critical factors to improve computation efficiency and memory bandwidth. Experiments on Intel/AMD x86 and ARM AArch64 platforms show that SpV8 outperforms several state-of-the-art approaches with large margins, achieving average <inline-formula><tex-math notation="LaTeX">$3.4\times$</tex-math></inline-formula> over Intel Math Kernel Library and <inline-formula><tex-math notation="LaTeX">$1.4\times$</tex-math></inline-formula> over the best existing approach. Such results indicate that the proposed model is capable of valuable guidance for efficient SpMV optimizations.

Comparative study of non-convex penalties and related algorithms in compressed sensing

Non-convex penalties are widely used in sparse representation models and fields such as compressed sensing, because they can efficiently recover signals with a high sparsity level compared with the well-known ℓ1-norm. However, few classic penalties have been selected in most applications without exploring the performance of other non-convex penalties. Therefore, the objective of this study is to provide a comparative and comprehensive study on non-convex penalties. We first collected nine representative non-convex penalties and then applied two optimization frameworks: the difference of convex function algorithm (DCA) and iterative shrinkage/thresholding algorithm (ISTA) to solve the optimization problems associated with the nine non-convex penalties. The performances of the nine penalties and two algorithms were systematically compared and analyzed experimentally. We hope that these results that concern non-convex penalty selection in sparse representation models can be used as a general reference for research.

MetaSEM: Gene Regulatory Network Inference from Single-Cell RNA Data by Meta-Learning.

Regulators in gene regulatory networks (GRNs) are crucial for identifying cell states. However, GRN inference based on scRNA-seq data has several problems, including high dimensionality and sparsity, and requires more label data. Therefore, we propose a meta-learning GRN inference framework to identify regulatory factors. Specifically, meta-learning solves the parameter optimization problem caused by high-dimensional sparse data features. In addition, a few-shot solution was used to solve the problem of lack of label data. A structural equation model (SEM) was embedded in the model to identify important regulators. We integrated the parameter optimization strategy into the bi-level optimization to extract the feature consistent with GRN reasoning. This unique design makes our model robust to small-scale data. By studying the GRN inference task, we confirmed that the selected regulators were closely related to gene expression specificity. We further analyzed the GRN inferred to find the important regulators in cell type identification. Extensive experimental results showed that our model effectively captured the regulator in single-cell GRN inference. Finally, the visualization results verified the importance of the selected regulators for cell type recognition.

Correspondence analysis for dimension reduction, batch integration, and visualization of single-cell RNA-seq data

Effective dimension reduction is essential for single cell RNA-seq (scRNAseq) analysis. Principal component analysis (PCA) is widely used, but requires continuous, normally-distributed data; therefore, it is often coupled with log-transformation in scRNAseq applications, which can distort the data and obscure meaningful variation. We describe correspondence analysis (CA), a count-based alternative to PCA. CA is based on decomposition of a chi-squared residual matrix, avoiding distortive log-transformation. To address overdispersion and high sparsity in scRNAseq data, we propose five adaptations of CA, which are fast, scalable, and outperform standard CA and glmPCA, to compute cell embeddings with more performant or comparable clustering accuracy in 8 out of 9 datasets. In particular, we find that CA with Freeman–Tukey residuals performs especially well across diverse datasets. Other advantages of the CA framework include visualization of associations between genes and cell populations in a “CA biplot,” and extension to multi-table analysis; we introduce corralm for integrative multi-table dimension reduction of scRNAseq data. We implement CA for scRNAseq data in corral, an R/Bioconductor package which interfaces directly with single cell classes in Bioconductor. Switching from PCA to CA is achieved through a simple pipeline substitution and improves dimension reduction of scRNAseq datasets.

Altered intestinal microbiota composition with epilepsy and concomitant diarrhea and potential indicator biomarkers in infants.

The diversity and dysregulation of intestinal microbiota is related to the pathology of epilepsy. Gut microbiota plays an important role in epilepsy, and regulating intestinal microbiota through exogenous intervention can alleviate symptoms. However, there are no studies about the effects of epilepsy-related diarrhea on gut microbiota. The diversity and dysregulation of intestinal microbiota is related to the pathology of epilepsy. Gut microbiota plays an important role in epilepsy, and regulating intestinal microbiota through exogenous intervention can alleviate symptoms. However, there are no studies about the effects of epilepsy-related diarrhea on gut microbiota. To evaluate changes in gut microbiota structure and composition in patients with epilepsy and associated diarrhea, the structure and composition of the fecal microbiota among patients with epilepsy (EP, 13 cases), epilepsy with diarrhea (ED, 13 cases), and probiotic treatments (PT, 13 cases), and healthy controls (CK, seven cases) were investigated and validated by utilizing high-throughput 16S rRNA sequencing. The results showed that the α-diversity indexes indicated that richness and phylogenetic diversity had no significant differences among groups. However, the variation of β-diversity indicated that the structure and composition of intestinal microbiota were significantly different among the CK, EP, ED, and PT groups (permutational multivariate analysis of variance, p-value = 0.001). Normalized stochasticity ratio and β-nearest taxon index indicated that stochastic mechanisms exerted increasing influence on community differences with epilepsy and associated diarrhea. ED microbiome alterations include increased Proteobacteria and decreased Actinobacteria and Firmicutes at the phylum level. Bifidobacterium was the core microbe in CK, EP, and PT, whereas it decreased significantly in ED. In contrast, Escherichia/Shigella was the core microbe in CK and ED, whereas it increased significantly in ED (Tukey's multiple comparisons test, adjusted p-value <0.05). The association network in CK has higher complexity and aggregation than in the other groups. The EP network indicated high connectivity density within each community and high sparsity among communities. The bacterial community network of the ED had a more compact local interconnection, which was in contrast to that of PT. The top 7 microbial amplicon sequence variant-based markers that were selected by machine learning to distinguish the groups of epilepsy, probiotic treatments, and healthy infants had stronger discrimination ability. In addition, ASVs_1 (Escherichia/Shigella) and ASVs_3 (Bifidobacterium) had the most importance in the recognition. Our research finally showed that infants with epilepsy, epilepsy with diarrhea, and probiotic treatments exhibit substantial alterations of intestinal microbiota structure and composition, and specific intestinal strains are altered according to different clinical phenotypes and can therefore be used as potential biomarkers for disease diagnosis.

ScDCCA: deep contrastive clustering for single-cell RNA-seq data based on auto-encoder network.

The advances in single-cell ribonucleic acid sequencing (scRNA-seq) allow researchers to explore cellular heterogeneity and human diseases at cell resolution. Cell clustering is a prerequisite in scRNA-seq analysis since it can recognize cell identities. However, the high dimensionality, noises and significant sparsity of scRNA-seq data have made it a big challenge. Although many methods have emerged, they still fail to fully explore the intrinsic properties of cells and the relationship among cells, which seriously affects the downstream clustering performance. Here, we propose a new deep contrastive clustering algorithm called scDCCA. It integrates a denoising auto-encoder and a dual contrastive learning module into a deep clustering framework to extract valuable features and realize cell clustering. Specifically, to better characterize and learn data representations robustly, scDCCA utilizes a denoising Zero-Inflated Negative Binomial model-based auto-encoder to extract low-dimensional features. Meanwhile, scDCCA incorporates a dual contrastive learning module to capture the pairwise proximity of cells. By increasing the similarities between positive pairs and the differences between negative ones, the contrasts at both the instance and the cluster level help the model learn more discriminative features and achieve better cell segregation. Furthermore, scDCCA joins feature learning with clustering, which realizes representation learning and cell clustering in an end-to-end manner. Experimental results of 14 real datasets validate that scDCCA outperforms eight state-of-the-art methods in terms of accuracy, generalizability, scalability and efficiency. Cell visualization and biological analysis demonstrate that scDCCA significantly improves clustering and facilitates downstream analysis for scRNA-seq data. The code is available at https://github.com/WJ319/scDCCA.

Pairwise ratio-based differential abundance analysis of infant microbiome 16S sequencing data.

Differential abundance analysis of infant 16S microbial sequencing data is complicated by challenging data properties, including high sparsity, extreme dispersion and the relative nature of the information contained within the data. In this study, we propose a pairwise ratio analysis that uses the compositional data analysis principle of subcompositional coherence and merges it with a beta-binomial regression model. The resulting method provides a flexible and easily interpretable approach to infant 16S sequencing data differential abundance analysis that does not require zero imputation. We evaluate the proposed method using infant 16S data from clinical trials and demonstrate that the proposed method has the power to detect differences, and demonstrate how its results can be used to gain insights. We further evaluate the method using data-inspired simulations and compare its power against related methods. Our results indicate that power is high for pairwise differential abundance analysis of taxon pairs that have a large abundance. In contrast, results for sparse taxon pairs show a decrease in power and substantial variability in method performance. While our method shows promising performance on well-measured subcompositions, we advise strong filtering steps in order to avoid excessive numbers of underpowered comparisons in practical applications.